© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 18470
    Prev
    Next
    INDEX
    Explanations

    female Japanese names commonly found in anime and manga

    oai_token-act-pair · gpt-3.5-turbo

    names of Japanese creators, particularly in the animation and manga industries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Colorado
    -0.84
     fec
    -0.73
     Colorado
    -0.71
    ulence
    -0.68
     grains
    -0.66
    Ħ¢
    -0.66
     FedEx
    -0.65
    olit
    -0.65
    sylv
    -0.65
     Nebraska
    -0.65
    POSITIVE LOGITS
     Tsuk
    1.30
    ichi
    1.24
     Yosh
    1.23
    oka
    1.17
    ji
    1.15
     Akira
    1.15
    jin
    1.10
    ishi
    1.10
     Tanaka
    1.10
     Tsu
    1.08
    Activations Density 0.167%

    No Known Activations